CN110298455B - Mechanical equipment fault intelligent early warning method based on multivariate estimation prediction - Google Patents
Mechanical equipment fault intelligent early warning method based on multivariate estimation prediction Download PDFInfo
- Publication number
- CN110298455B CN110298455B CN201910572423.3A CN201910572423A CN110298455B CN 110298455 B CN110298455 B CN 110298455B CN 201910572423 A CN201910572423 A CN 201910572423A CN 110298455 B CN110298455 B CN 110298455B
- Authority
- CN
- China
- Prior art keywords
- mechanical equipment
- prediction
- data
- early warning
- modeling
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
An intelligent mechanical equipment fault early warning method based on multivariate estimation prediction comprises the following steps: step 1, modeling a data subset; step 2, preprocessing the modeling data subset: step 3, constructing a prediction model of mechanical equipment state parameters and working condition parameters: step 4, estimating and predicting the actual measurement state parameters corresponding to the state parameters of the mechanical equipment in the normal operation state; step 5, subtracting the actual measurement result and the prediction result of the state parameter to obtain a residual error value of the state parameter, judging whether the absolute magnitude and the growth trend of the residual error exceed corresponding thresholds, further detecting the fault abnormality of the equipment and implementing alarm; the intelligent early warning model of the mechanical equipment is built based on the multivariable estimation prediction method, so that intelligent early warning of the failure of the mechanical equipment under the variable working conditions is realized. Compared with the traditional mechanical equipment fault early warning method, the method has the advantages of high prediction precision, high early warning accuracy and more timely early warning.
Description
Technical Field
The invention belongs to the field of mechanical equipment early warning, and particularly relates to a mechanical equipment fault intelligent early warning method based on multivariate estimation prediction.
Background
In the field of predictive maintenance of mechanical equipment, aiming at abnormal state detection of the mechanical equipment, a traditional early warning mode is a hard threshold alarm or a trend alarm. The hard threshold alarm is generally to determine an international standard or national standard alarm threshold applicable to vibration monitoring parameters (displacement, speed or acceleration) of the equipment according to the type of the equipment, and determine an alarm threshold corresponding to the equipment according to information such as the working rotating speed, power and the like of the equipment. Some enterprises can formulate more applicable enterprise standard alarm thresholds according to equipment operation conditions accumulated for many years and by combining with field experience of engineers. Trend alarms are alarms implemented by monitoring the state monitoring parameters for overrun in the growing trend. The traditional early warning mode is only suitable for stable working condition equipment, and can not solve the problem of abnormal fault detection of variable working condition mechanical equipment (such as equipment motor rotation speed change, load change, current change and the like).
Disclosure of Invention
The invention aims to provide an intelligent mechanical equipment fault early warning method based on multivariate estimation prediction so as to solve the problems.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
an intelligent mechanical equipment fault early warning method based on multivariate estimation prediction comprises the following steps:
step 3, constructing a prediction model of mechanical equipment state parameters and working condition parameters: selecting the normalized modeling training data set to establish a corresponding normal running space matrix D;
and 4, estimating and predicting the actually measured state parameters corresponding to the state parameters of the mechanical equipment in the normal running state.
Step 5, subtracting the actual measurement result and the prediction result of the state parameter to obtain a residual error value of the state parameter, judging whether the absolute magnitude and the growth trend of the residual error exceed corresponding thresholds, further detecting the fault abnormality of the equipment and implementing alarm;
Further, the step 1 specifically includes: selecting a historical operation data set of 1 to 3 months under normal operation of mechanical equipment, wherein the historical operation data set comprises mechanical equipment state parameters and partial working condition data corresponding to the mechanical equipment, and the mechanical equipment state parameters specifically comprise: acceleration peak value, speed effective value and displacement of each measuring point in vibration monitoring of mechanical equipmentPeak characteristic parameters; the partial working condition data corresponding to the mechanical equipment comprises motor current, motor power, motor rotating speed and motor load parameters; dividing the data set by using the motor rotation speed P, wherein P is less than or equal to 0 and is divided into equipment shutdown states, and the corresponding data are not included in the modeling data set; p (P)>0 is divided into equipment running states, and corresponding data are included in a modeling data set; removing all abnormal data points in the modeling data set to obtain a final modeling subset x, and dividing the modeling subset into modeling training data sets x according to the proportion of a percent to b percent train And model test dataset x test Wherein a++b% = 100% and a%>b％。
Further, in step 2:
the normalization method comprises the following steps:
where j represents the selected variable, i represents the sequence number of the selected variable, x ji X is the raw data not normalized jmax To select the maximum value of the variable j sequence, x jmin To select the minimum value of the variable j sequence, X ji Normalized variable values.
Further, in step 3:
the construction method of D comprises the following steps:
wherein each column of D represents a normal state sample of the modeled data subset, which consists of n variables, D representing a total of m sample sets;
in the formula (1)
The Euclidean distance between two vectors is calculated, the Euclidean distance between the X vector and the Y vector is calculated as a column description, and the calculation formula is as follows:
test data set X to be reserved test Inputting the model, and calculating by the following formula (1) to obtain a corresponding prediction result X predict ；
And then checking whether the prediction error of the test data set meets the requirement, setting the prediction relative error of the state parameters to be less than or equal to 2%, setting the prediction relative error of the working condition parameters to be less than or equal to 5%, if the prediction error meets the requirement, indicating that the constructed model meets the application requirement, if the prediction error does not meet the requirement, continuing to correct the modeling, and repeating the steps 1, 2 and 3 until the prediction error of the test set meets the requirement, and ending the modeling.
Further, in step 4:
firstly, an array X consisting of actual measurement state parameters and corresponding actual measurement working condition parameters measure Inputting the prediction calculation formula into a prediction model to predict, wherein the prediction calculation formula is as follows:
further, the residual error setting threshold calculating method in the step 6 is as follows:
selecting a section of data of normal operation of mechanical equipment, inputting the data consisting of state parameters and working condition parameters into a model to obtain a prediction result, wherein a prediction calculation formula is the same as the prediction formula in the step 4; subtracting the actual measurement result of each state parameter from the corresponding predicted result to obtain a residual sequence, and calculating the residual average value mu of each state parameter i And standard deviation sigma i The threshold value for each state parameter is:
threshold i ＝μ i +k×σ i wherein the subscript i denotes a certain class of state parameters, k denotes how many coefficients of the normal data amount are selected for inclusion in the residual alarm threshold, and the greater k isThe larger the data volume is, the value of k is 2,3,4,5 and 6;
the residual calculation method comprises the following steps: r=x measure -X forcast 。
Further, the method for calculating the growing trend of the residual error in the step 6 is as follows:
wherein r is his For a section of historical data containing the residual error result at the current moment and n previous moments, n represents the length of a window for selecting and calculating the growth trend data, and the value of n is 5-10; the range of the trend threshold value can be 50% -100%.
Compared with the prior art, the invention has the following technical effects:
according to the intelligent early warning method, an intelligent early warning model of the mechanical equipment is established based on the multivariate estimation prediction method, and further intelligent early warning of the faults of the mechanical equipment under variable working conditions is achieved. Compared with the traditional mechanical equipment fault early warning method, the method predicts the measured data by training and learning modeling of the historical normal data and adopting the parameter-free multivariable prediction method, has the advantages of high prediction precision and high early warning accuracy, and can extract hidden abnormal information from the changed working conditions due to the fact that working condition parameters are included in the modeling and prediction process, so that early warning is realized more timely and earlier.
Meanwhile, the intelligent early warning method can solve the problem that abnormal information of variable working condition equipment is covered by working conditions, so that abnormality cannot be detected and found. By the application of the invention, early prediction discovery of fault abnormality of the variable working condition mechanical equipment can be realized, decision basis is provided for maintenance of the mechanical equipment, potential safety hazard of the equipment is effectively reduced, and abnormal shutdown and great economic loss of the equipment are avoided.
Drawings
FIG. 1 is a flow chart of intelligent early warning of mechanical equipment faults based on multivariate estimation prediction
FIG. 2 is a diagram illustrating the relationship between vibration acceleration and operating parameters of a mechanical device
FIG. 3 verification of a multivariate model of vibration acceleration of a machine
FIG. 4 vibration acceleration residual trend of a mechanical device
Detailed Description
The invention is further described below with reference to the accompanying drawings:
referring to fig. 1 to 4, an intelligent mechanical equipment fault early warning method based on multivariate estimation prediction includes the following steps:
step 3, constructing a prediction model of mechanical equipment state parameters and working condition parameters: selecting the normalized modeling training data set to establish a corresponding normal running space matrix D;
and 4, estimating and predicting the actually measured state parameters corresponding to the state parameters of the mechanical equipment in the normal running state.
Step 5, subtracting the actual measurement result and the prediction result of the state parameter to obtain a residual error value of the state parameter, judging whether the absolute magnitude and the growth trend of the residual error exceed corresponding thresholds, further detecting the fault abnormality of the equipment and implementing alarm;
The step 1 specifically comprises the following steps: selecting a historical operation data set of 1-3 months under normal operation of the mechanical equipment, wherein the historical operation data set comprises state parameters of the mechanical equipment and the mechanical equipmentAnd partial working condition data corresponding to the equipment, wherein the state parameters of the mechanical equipment specifically comprise: acceleration peak value, speed effective value and displacement peak characteristic parameters of each measuring point in vibration monitoring of mechanical equipment; the corresponding part of working condition data of the mechanical equipment comprises motor current, motor power, motor rotating speed and motor load parameters; dividing the data set by using the motor rotation speed P, wherein P is less than or equal to 0 and is divided into equipment shutdown states, and the corresponding data are not included in the modeling data set; p (P)>Dividing into equipment running states, and enabling corresponding data to be included in a modeling data set; removing all abnormal data points in the modeling data set to obtain a final modeling subset x, and dividing the modeling subset into modeling training data sets x according to the proportion of a percent to b percent train And model test dataset x test Wherein a++b% = 100% and a%>b％。
In step 2:
the normalization method comprises the following steps:
where j represents the selected variable, i represents the sequence number of the selected variable, x ji X is the raw data not normalized jmax To select the maximum value of the variable j sequence, x jmin To select the minimum value of the variable j sequence, X ji Normalized variable values.
In step 3:
the construction method of D comprises the following steps:
wherein each column of D represents a normal state sample of the modeled data subset, which consists of n variables, D representing a total of m sample sets;
in the formula (1)
The Euclidean distance between the two vectors is calculated, the Euclidean distance between the X and Y vectors is calculated as the column description, and the calculation formula is as follows：
Test data set X to be reserved test Inputting the model, and calculating by the following formula (1) to obtain a corresponding prediction result X predict ；
And then checking whether the prediction error of the test data set meets the requirement, setting the prediction relative error of the state parameters to be less than or equal to 2%, setting the prediction relative error of the working condition parameters to be less than or equal to 5%, if the prediction error meets the requirement, indicating that the constructed model meets the application requirement, if the prediction error does not meet the requirement, continuing to correct the modeling, and repeating the steps 1, 2 and 3 until the prediction error of the test set meets the requirement, and ending the modeling.
In step 4:
firstly, an array X consisting of actual measurement state parameters and corresponding actual measurement working condition parameters measure Inputting the prediction calculation formula into a prediction model to predict, wherein the prediction calculation formula is as follows:
the residual error setting threshold calculating method in the step 6 is as follows:
selecting a section of data of normal operation of mechanical equipment, inputting the data consisting of state parameters and working condition parameters into a model to obtain a prediction result, wherein a prediction calculation formula is the same as the prediction formula in the step 4; subtracting the actual measurement result of each state parameter from the corresponding predicted result to obtain a residual sequence, and calculating the residual average value mu of each state parameter i And standard deviation sigma i The threshold value for each state parameter is:
threshold i ＝μ i +k×σ i wherein the subscript i denotes a certain class of stateThe parameter, k, represents the residual error alarm threshold value and comprises a coefficient for selecting the quantity of normal data, and the greater k is, the greater the contained data quantity is, and the value of k is 2,3,4,5 and 6;
the residual calculation method comprises the following steps: r=x measure -X forcast 。
The calculation method of the residual error growing trend in the step 6 is as follows:
wherein r is his For a section of historical data containing the residual error result at the current moment and n previous moments, n represents the length of a window for selecting and calculating the growth trend data, and the value of n is 5-10; the range of the trend threshold value can be 50% -100%.
See fig. 1. FIG. 1 is a flow chart of intelligent early warning of mechanical equipment failure based on multivariate estimation prediction. And selecting a historical data set of the mechanical equipment in a normal working state for 1 to 6 months as a modeling data candidate set, wherein the modeling data candidate set comprises mechanical equipment state parameters (such as vibration acceleration, speed, displacement and the like of each measuring point of the equipment) and working condition data (such as motor power, current, rotating speed and the like) related to the equipment state, and dividing the modeling data candidate set into a training set and a testing set. And carrying out normalization pretreatment on modeling data, establishing a multivariate prediction model by utilizing normalized training data, and verifying whether the accuracy of the prediction model meets the modeling accuracy requirement by utilizing test data. When the acquisition of the actual measurement data is completed, the actual measurement parameters can be input into a verified prediction model, the model outputs corresponding prediction results, the actual measurement results and the prediction results are differenced, residual error values of the parameters are obtained, whether the obtained residual errors are larger than a set threshold value or not is judged, the state of the equipment is abnormal if the obtained residual errors are larger than the threshold value, alarm information is deduced, and otherwise, the equipment is normal.
See fig. 2. FIG. 2 is a graph showing the relationship between vibration acceleration and operating mode parameters of a certain mechanical device. The current, the power and the rotating speed of the driving motor of the equipment are in a continuously-changing state, so that the vibration acceleration of the equipment also changes along with the change of working conditions, and the fluctuation is severe.
See fig. 3. In the method, the prediction result and the actual measurement result of the vibration acceleration multivariable model of certain mechanical equipment are verified, the prediction vibration value and the actual measurement vibration value are all overlapped, the maximum prediction error is only 1%, and the model prediction precision requirement is met.
See fig. 4. FIG. 4 is a graph showing the residual trend of vibration acceleration of a mechanical device, wherein the early vibration residual is close to 0, and the device is in a normal working state; the equipment in the later stage is abnormal, the vibration residual value exceeds a set threshold value to trigger an alarm, and the abnormal detection and the intelligent fault early warning of the variable working condition equipment are realized.
Claims (6)
1. An intelligent mechanical equipment fault early warning method based on multivariate estimation prediction is characterized by comprising the following steps:
step 1, selecting a mechanical equipment state parameter and partial working condition data corresponding to the mechanical equipment in a normal working state of the mechanical equipment, and modeling a data subset, wherein a historical operation data set of 1 to 3 months under normal operation of the mechanical equipment is selected, and the historical operation data set comprises the mechanical equipment state parameter and the partial working condition data corresponding to the mechanical equipment, wherein the mechanical equipment state parameter specifically comprises: acceleration peak value, speed effective value and displacement peak characteristic parameters of each measuring point in vibration monitoring of mechanical equipment; the partial working condition data corresponding to the mechanical equipment comprises motor current, motor power, motor rotating speed and motor load parameters; dividing the data set by using the motor rotation speed P, wherein P is less than or equal to 0 and is divided into equipment shutdown states, and the corresponding data are not included in the modeling data set; p >0 is divided into equipment running states, and corresponding data are included in a modeling data set; removing all abnormal data points in the modeling data set to obtain a final modeling subset x, and dividing the modeling subset into a modeling training data set xtrain and a model test data set xtest according to the proportion of a%: b%, wherein a% +b% = 100%, and a% > b%;
step 2, preprocessing the modeling data subset: performing min-max standardization on each variable characteristic of the modeling data subset, and normalizing to a [0,1] interval;
step 3, constructing a prediction model of mechanical equipment state parameters and working condition parameters: selecting the normalized modeling training data set to establish a corresponding normal running space matrix D;
step 4, estimating and predicting the actual measurement state parameters corresponding to the state parameters of the mechanical equipment in the normal operation state;
step 5, subtracting the actual measurement result and the prediction result of the state parameter to obtain a residual error value of the state parameter, judging whether the absolute magnitude and the growth trend of the residual error exceed corresponding thresholds, further detecting the fault abnormality of the equipment and implementing alarm;
step 6, judging whether the residual result exceeds a set threshold value, if so, the mechanical equipment has faults and abnormality and needs to be alarmed; otherwise, the mechanical equipment is in normal operation without alarm; meanwhile, judging whether the increasing trend of the residual error exceeds a set trend threshold value, and if the increasing trend exceeds the set trend threshold value, giving an alarm when the mechanical equipment is abnormally and continuously deteriorated; otherwise, the mechanical equipment is free from abnormal degradation and alarm.
2. The intelligent mechanical equipment fault early warning method based on multivariate estimation prediction according to claim 1, wherein in step 2:
the normalization method comprises the following steps:
where j represents the selected variable, i represents the sequence number of the selected variable, xji is the non-normalized raw data, xjmax is the maximum value of the selected variable j sequence, xjmin is the minimum value of the selected variable j sequence, and Xji is the normalized variable value.
3. The intelligent mechanical equipment fault early warning method based on multivariate estimation prediction according to claim 1, wherein in step 3:
the construction method of D comprises the following steps:
wherein each column of D represents a normal state sample of the modeled data subset, which consists of n variables, D representing a total of m sample sets;
in the expression (1), the Euclidean distance between the two vectors is calculated, and the Euclidean distance between the two vectors of X and Y is calculated as a column description,
the calculation formula is as follows:
inputting the reserved test data set Xtest into a model, and calculating to obtain a corresponding prediction result Xprediction through the following formula (1);
and then checking whether the prediction error of the test data set meets the requirement, setting the prediction relative error of the state parameters to be less than or equal to 2%, setting the prediction relative error of the working condition parameters to be less than or equal to 5%, if the prediction error meets the requirement, indicating that the constructed model meets the application requirement, if the prediction error does not meet the requirement, continuing to correct the modeling, and repeating the steps 1, 2 and 3 until the prediction error of the test set meets the requirement, and ending the modeling.
4. The intelligent mechanical equipment fault early warning method based on multivariate estimation prediction according to claim 1, wherein in step 4:
firstly, inputting an array Xmeasure formed by actual measurement state parameters and corresponding actual measurement working condition parameters into a prediction model for prediction, wherein a prediction calculation formula is as follows:
5. the intelligent mechanical equipment fault early warning method based on multivariate estimation prediction according to claim 1, wherein the residual error setting threshold calculation method in the step 5 is as follows:
selecting a section of data of normal operation of mechanical equipment, inputting the data consisting of state parameters and working condition parameters into a model to obtain a prediction result, wherein a prediction calculation formula is the same as the prediction formula in the step 4; subtracting the actual measurement result and the corresponding prediction result of each state parameter to obtain a residual sequence, and calculating a residual mean value mu i and a standard deviation sigma i of each state parameter, wherein the threshold value of each state parameter is as follows:
threshold=μi+k×σi, where the subscript i represents a certain type of state parameter, k represents how many coefficients of the normal data volume are selected to be included in the residual alarm threshold, and the greater k is, the greater the included data volume is, the greater k is, and the values of k are 2,3,4,5, and 6;
the residual calculation method comprises the following steps: r=xmeasure-Xforcast.
6. The intelligent early warning method for mechanical equipment faults based on multivariate estimation prediction according to claim 1, wherein the calculation method for the growing trend of the residual errors in the step 6 is as follows:
wherein, the rhis is a section of history data containing the residual error result at the current moment and n times before, n represents the length of a window for selecting and calculating the growth trend data, and the value of n is 5-10; the range of the trend threshold value can be 50% -100%.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910572423.3A CN110298455B (en) | 2019-06-28 | 2019-06-28 | Mechanical equipment fault intelligent early warning method based on multivariate estimation prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910572423.3A CN110298455B (en) | 2019-06-28 | 2019-06-28 | Mechanical equipment fault intelligent early warning method based on multivariate estimation prediction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110298455A CN110298455A (en) | 2019-10-01 |
| CN110298455B true CN110298455B (en) | 2023-06-02 |
Family
ID=68029197
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910572423.3A Active CN110298455B (en) | 2019-06-28 | 2019-06-28 | Mechanical equipment fault intelligent early warning method based on multivariate estimation prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110298455B (en) |
Families Citing this family (37)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110579367A (en) * | 2019-09-23 | 2019-12-17 | 北京国电龙源环保工程有限公司 | Fault self-diagnosis system and method for drying bed |
| CN110737976B (en) * | 2019-10-10 | 2023-12-08 | 西安因联信息科技有限公司 | Mechanical equipment health assessment method based on multidimensional information fusion |
| CN110658807A (en) * | 2019-10-16 | 2020-01-07 | 上海仁童电子科技有限公司 | Vehicle fault diagnosis method, device and system |
| CN110907207B (en) * | 2019-11-25 | 2022-08-09 | 湃方科技(天津)有限责任公司 | Running state detection method and device for non-marking mechanical equipment |
| CN111090939B (en) * | 2019-12-17 | 2023-08-15 | 上海汉中诺软件科技有限公司 | Early warning method and system for abnormal working condition of petrochemical device |
| CN111396266A (en) * | 2020-03-05 | 2020-07-10 | 浙江运达风电股份有限公司 | GBRT-based wind turbine generator bearing fault early warning method |
| CN113406537B (en) * | 2020-03-16 | 2024-05-07 | 上海长庚信息技术股份有限公司 | Quantitative evaluation method for fault degree of power equipment |
| CN111597223A (en) * | 2020-04-10 | 2020-08-28 | 神华国能集团有限公司 | Fault early warning processing method, device and system |
| US11717966B2 (en) | 2020-05-07 | 2023-08-08 | Mujin, Inc. | Method and computing system for determining a value of an error parameter indicative of quality of robot calibration |
| CN113821006B (en) * | 2020-05-07 | 2022-10-14 | 牧今科技 | Method and computing system for determining values of error parameters indicative of robot calibration quality |
| CN111915052B (en) * | 2020-05-26 | 2023-05-02 | 南方电网调峰调频发电有限公司 | Self-adaptive test method for intelligent prediction algorithm of analog measurement value |
| CN111720296B (en) * | 2020-06-11 | 2022-03-08 | 浙江浙能技术研究院有限公司 | Steam feed pump equipment abnormal state early warning method based on self-encoder |
| CN111814848B (en) * | 2020-06-22 | 2024-04-09 | 浙江大学 | Self-adaptive early warning strategy design method for temperature faults of wind turbine generator |
| CN111814849B (en) * | 2020-06-22 | 2024-02-06 | 浙江大学 | DA-RNN-based wind turbine generator set key component fault early warning method |
| CN111985546A (en) * | 2020-08-10 | 2020-11-24 | 西北工业大学 | Aircraft engine multi-working-condition detection method based on single-classification extreme learning machine algorithm |
| CN112017409A (en) * | 2020-08-25 | 2020-12-01 | 西安因联信息科技有限公司 | Trend early warning method for short-time increase amplitude of mechanical equipment vibration |
| CN112040351B (en) * | 2020-08-25 | 2022-04-26 | 西安因联信息科技有限公司 | Mechanical equipment vibration alarm information pushing method |
| CN112504505A (en) * | 2020-08-31 | 2021-03-16 | 中国能源建设集团安徽省电力设计院有限公司 | High-voltage tunnel cable overheating early warning method based on multivariate state estimation |
| CN112067335A (en) * | 2020-09-03 | 2020-12-11 | 华能国际电力股份有限公司玉环电厂 | Power plant blower fault early warning method based on multivariate state estimation |
| CN112131270A (en) * | 2020-09-14 | 2020-12-25 | 武汉第二船舶设计研究所(中国船舶重工集团公司第七一九研究所) | Intelligent numerical prediction method and system suitable for marine nuclear power platform |
| CN112257943A (en) * | 2020-10-29 | 2021-01-22 | 上海电力大学 | Power plant induced draft fan fault early warning method based on MSET and deviation degree |
| CN112525336B (en) * | 2020-11-18 | 2023-06-27 | 西安因联信息科技有限公司 | Automatic detection method for continuous vibration growth of mechanical equipment |
| CN112525334B (en) * | 2020-11-18 | 2023-06-02 | 西安因联信息科技有限公司 | Dynamic equipment vibration multistable detection method |
| CN112629585A (en) * | 2020-12-02 | 2021-04-09 | 三门核电有限公司 | Equipment on-line monitoring method and device based on multi-dimensional parameter estimation |
| CN112633561A (en) * | 2020-12-09 | 2021-04-09 | 北京名道恒通信息技术有限公司 | Production risk intelligent prediction early warning method based on industrial big data |
| CN112905958B (en) * | 2021-01-27 | 2024-04-19 | 南京国电南自电网自动化有限公司 | Short-time data window telemetry data state identification method and system based on measurement and control device |
| CN113031552B (en) * | 2021-03-09 | 2022-10-25 | 浙江菲达环保科技股份有限公司 | Cooperative control method and system for environmental protection equipment behind furnace |
| CN113033673B (en) * | 2021-03-24 | 2022-10-25 | 河南中烟工业有限责任公司 | Training method and system for motor working condition abnormity detection model |
| EP4083584A1 (en) | 2021-04-29 | 2022-11-02 | Mettler-Toledo Garvens GmbH | Method for evaluating the performance of a dynamic weighing instrument, weighing system and computer program |
| CN113219334A (en) * | 2021-05-06 | 2021-08-06 | 南京航空航天大学 | Wallboard molded surface loading state early warning method based on push rod loading current |
| CN114139591A (en) * | 2021-06-23 | 2022-03-04 | 核动力运行研究所 | Mechanical equipment state early warning method |
| CN113468022B (en) * | 2021-07-01 | 2024-02-09 | 丁鹤 | Automatic operation and maintenance method for centralized monitoring of products |
| CN114002574A (en) * | 2021-10-29 | 2022-02-01 | 上海华力微电子有限公司 | Method for testing semiconductor structure |
| CN114064760B (en) * | 2021-11-18 | 2022-12-13 | 广州泰禾大数据服务有限公司 | Multi-dimensional early warning analysis and judgment method for data |
| CN115484146A (en) * | 2022-08-22 | 2022-12-16 | 中国船舶集团有限公司系统工程研究院 | Self-adaptive early warning method for state parameters of gas turbine under time-varying working condition |
| CN115817178A (en) * | 2022-11-14 | 2023-03-21 | 宁德时代新能源科技股份有限公司 | Fault early warning method and device, battery, vehicle and storage medium |
| CN115712268B (en) * | 2022-12-23 | 2023-04-14 | 深圳市创立宏科技有限公司 | Fault early warning system for automatic electronic product auxiliary material laminating device |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107609574A (en) * | 2017-08-18 | 2018-01-19 | 上海电力学院 | Wind turbines fault early warning method based on data mining |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AR091412A1 (en) * | 2013-06-11 | 2015-02-04 | Ypf Sa | DEVICE AND METHOD FOR DIAGNOSING ANOMAL SITUATIONS IN PROCESSES |
| CN104102773B (en) * | 2014-07-05 | 2017-06-06 | 山东鲁能软件技术有限公司 | A kind of equipment fault early-warning and state monitoring method |
| CN105719002A (en) * | 2016-01-18 | 2016-06-29 | 重庆大学 | Wind turbine generator state parameter abnormity identification method based on combination prediction |
| CN106444703B (en) * | 2016-09-20 | 2018-12-07 | 西南石油大学 | Dynamic equipment running status fuzzy evaluation and prediction technique based on fault mode probability of happening |
| CN108681633B (en) * | 2018-05-11 | 2022-03-29 | 上海电力学院 | Condensate pump fault early warning method based on state parameters |
| CN108869174B (en) * | 2018-06-15 | 2020-06-19 | 西安交通大学 | Nonlinear modeling wind driven generator blade natural frequency working condition compensation method |
-
2019
- 2019-06-28 CN CN201910572423.3A patent/CN110298455B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107609574A (en) * | 2017-08-18 | 2018-01-19 | 上海电力学院 | Wind turbines fault early warning method based on data mining |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110298455A (en) | 2019-10-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110298455B (en) | Mechanical equipment fault intelligent early warning method based on multivariate estimation prediction | |
| CN104932488B (en) | A kind of Model Predictive Control Performance Evaluation and diagnostic method | |
| CN107291991B (en) | Early defect early warning method for wind turbine generator based on dynamic network sign | |
| CN112598172A (en) | Wind turbine bearing temperature early warning method | |
| CN103678858A (en) | Method for predicting remaining life of equipment under competing failure conditions | |
| CN112883634B (en) | DC measurement system state prediction method and system based on multi-dimensional analysis | |
| CN111860839A (en) | Shore bridge fault monitoring method based on multi-signal fusion and Adam optimization algorithm | |
| CN111648992A (en) | Gas turbine compressor fault identification early warning method | |
| CN113374652A (en) | Method for evaluating service life of wind generating set | |
| CN114925718A (en) | Transformer core grounding current online prediction method and device, storage medium and fault diagnosis method | |
| CN112418306A (en) | Gas turbine compressor fault early warning method based on LSTM-SVM | |
| CN111855219A (en) | Diesel engine lubricating oil entering security parameter prediction method based on grey theory | |
| CN110987396A (en) | Intelligent fault diagnosis and service life prediction method for coal mining machine rocker arm | |
| CN111934903A (en) | Docker container fault intelligent prediction method based on time sequence evolution genes | |
| CN114962239B (en) | Equipment fault detection method based on intelligent Internet of things | |
| KR101967524B1 (en) | Apparatus and method for authenticating time-varying signal in online via kernel regression model | |
| CN115685045A (en) | Online evaluation method for voltage transformer | |
| KR20240003469A (en) | Predictive diagnosis method and system of nuclear power plant equipment | |
| CN114943281A (en) | Intelligent decision-making method and system for heat pipe cooling reactor | |
| CN115062533A (en) | Construction and prediction method and medium of multiple regression prediction model | |
| Hu et al. | Anomaly detection and remaining useful lifetime estimation based on degradation state for bearings | |
| CN114970311A (en) | Method for establishing remote module life prediction model and life prediction method | |
| CN114219206B (en) | Gray-level-analysis-based comprehensive evaluation method for oil system state of pumped storage unit | |
| CN112982544B (en) | Underground scraper fault diagnosis method based on KPCA | |
| CN109872004B (en) | Equipment fault prediction and health assessment method based on fuzzy Bayesian network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |